From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Mason Subject: Re: New to reiserfs Date: 14 May 2002 09:10:46 -0400 Message-ID: <1021381846.20175.572.camel@tiny> References: <200205132153.59075.Dieter.Nuetzel@hamburg.de> <3CE028A3.3080002@namesys.com> <200205132324.24309.Dieter.Nuetzel@hamburg.de> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: list-help: list-unsubscribe: list-post: In-Reply-To: <200205132324.24309.Dieter.Nuetzel@hamburg.de> List-Id: Content-Type: text/plain; charset="iso-8859-1" To: Dieter =?ISO-8859-1?Q?N=FCtzel?= Cc: Hans Reiser , Oleg Drokin , ReiserFS List , JPASTORM@esade.edu On Mon, 2002-05-13 at 17:24, Dieter N=FCtzel wrote: > > > > You should put squid into one big directory (not using their kludge tha= t > > avoids making directories too large by using a tree) >=20 > So you understand me right...;-) >=20 > > unless you have multiple processors (in which case the VFS directory gi= ant > > lock will hurt you). >=20 > BKL? >=20 > Where is the limit 2, 4, or even more CPUs? > I'll have two in some days. You probably want one directory per squid process. The VFS layer does semaphore locking to prevent races between people reading the directory and people changing the directory. If you've just got one big directory, all the squid processes will end up waiting on each other. More directories mean more time wasted changing the directory stat data, and ram wasted on reading the stat data. You see this more with hundreds or thousands of directories. -chris